INDEX

Explanations

references to dragons and related sculptures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

存于互联网档案馆

-0.95

Hochspringen

-0.86

 pinulongan

-0.86

 Audiodateien

-0.81

DebuggerNonUser

-0.80

tagHelperRunner

-0.78

ReusableCell

-0.76

ImageContext

-0.76

adpleegd

-0.75

unnitel

-0.75

POSITIVE LOGITS

wel

0.86

 Welding

0.78

 welding

0.75

 dragon

0.74

Ing

0.72

 Dragon

0.71

 hike

0.71

 weld

0.70

Wel

0.69

 hiked

0.69

Activations Density 0.093%

references to dragons and related sculptures

No Comments

No Known Activations